Heart rate variability (HRV) is a physiological measurement that can help to monitor and diagnose chronic diseases such as cardiovascular disease, depression, and psychological stress. HRV measurement is commonly extracted from the electrocardiography (ECG). However, ECG has bulky wires where it needs at least three surface electrodes to be placed on the skin. This may cause distraction during the recording and need longer time to setup. Therefore, photoplethysmography (PPG), a simple optical technique, was suggested to obtain heart rate. This study proposes to investigate the effectiveness of PPG recording and derivation of HRV for feature analysis. The PPG signal was preprocessed to remove all the noise and to extract the HRV. HRV features were collected using time-domain analysis (TA), frequency-domain analysis (FA) and nonlinear time-frequency analysis (TFA). Five out of 22 HRV features, which are HR, RMSSD, LF/HF, LFnu, and HFnu, showed high correlation (rho > 0.6 and prho < 0.05) in comparison to standard 5-min excerpt while producing significant difference (p-value < 0.05) during the stressing condition across all interval HRV excerpts. This simple yet accurate PPG recording system perhaps might useful to assess the HRV signal in a short time, and further can be used for the ANS assessment.

Adverse childhood experiences has been suggested to cause changes in physiological processes and can determine the magnitude of the stress response which might have a significant impact on health later in life. To detect the stress response, biomarkers that represent both Autonomic Nervous System (ANS) and Hypothalamic-Pituitary-Adrenal (HPA) axis is proposed. Among the available biomarkers, Heart Rate Variability (HRV) has been proven as a powerful biomarker that represents ANS. Meanwhile, salivary cortisol has been suggested as a biomarker that reflects the HPA axis. Even though many studies used multiple biomarkers to measure the stress response, the results for each biomarker were analysed separately. Therefore, the objective of this study is to propose a fusion of ANS and HPA axis biomarkers in order to classify the stress response based on adverse childhood experience. Electrocardiograph, blood pressure (BP), pulse rate (PR) and salivary cortisol (SCort) measures were collected from 23 healthy participants, 12 participants had adverse childhood experience while the remaining 11 acted as the no adversity control group. HRV was then computed from the ECG and the HRV features were extracted. Next, the selected HRV features were combined with the other biomarkers using Euclidean distance (e d) and serial fusion, and the performance of the fused features were compared using Support Vector Machine. From the result, HRV-SCort using Euclidean distance achieved the most satisfactory performance with 80.0% accuracy, 83.3% sensitivity and 78.3% specificity. Furthermore, the performance of the stress response classification of the fused biomarker, HRV-SCort, outperformed that of the single biomarkers: HRV (61% Accuracy), Cort (59.4% Accuracy), BP (78.3% accuracy) and PR (53.3% accuracy). From this study, it was proven that the fused biomarkers that represent both ANS and HPA (HRV-SCort) able to demonstrate a better classification performance in discriminating the stress response. Furthermore, a new approach for classification of stress response using Euclidean distance and SVM named as e d-SVM was proven to be an effective method for the HRV-SCort in classifying the stress response from PASAT. The robustness of this method is crucial in contributing to the effectiveness of the stress response measures and could further be used as an indicator for future health.

Autism spectrum disorder (ASD) is a developmental disability that involves persistent challenges in social interaction, communication and behaviour. The purpose of this study is to apply a machine learning approach to differentiate between autistic and normal children and to evaluate the performance of different classifiers in the detection of autism disorder. Heart Rate Variability (HRV) analysis is one of the strategies used for ASD detection by assessing the autonomic nervous system (ANS), which serves as a biomarker for the autism phenotype. HRV can be derived from the photoplethysmogram (PPG). Logistic Regression, Linear Discriminant Analysis and a Cubic Support Vector Machine (SVM) were chosen to evaluate the performance of HRV features in differentiating between normal and autistic children. Three different combinations of features were selected out of 19 features in total. From the results, Logistic Regression was the best classifier to differentiate between autistic and normal children in a colour stimulus test with 100% accuracy, while Linear Discriminant Analysis was best suited in the baseline test with 90% accuracy. In conclusion, the machine learning approach could be an alternative method of making an early diagnosis of ASD in the near future.

No abstract

No abstract